论文部分内容阅读
晶粒度是高强度铝合金微观组织分析的关键参数。通常是由人工手动获得,整个过程耗时且容易出错。目前随着数字图像处理技术和模式识别技术的快速发展,为定量金相分析提供了一种新的方法。利用人工智能实现自动金相分析可以克服手工工艺的缺点。在本文中提出了确定的金相图像的晶粒尺寸的数字图像处理的一种新方法。基于模糊逻辑的边缘检测算法的提取晶界。并对不同方法的金相图像提取方法进行了对比,验证了该方法的有效性。并基于美国材料试验学会(ASTM)标准获得了晶粒度等微观组织参数。
Grain size is a key parameter in microstructure analysis of high-strength aluminum alloys. It is usually manually obtained manually, and the whole process is time consuming and error prone. At present, with the rapid development of digital image processing technology and pattern recognition technology, a new method for quantitative metallographic analysis is provided. The use of artificial intelligence to achieve automatic metallographic analysis can overcome the shortcomings of the manual process. In this paper, a new method of digital image processing for determining the grain size of a metallographic image is proposed. Extraction of Grain Boundaries Based on Fuzzy Logical Edge Detection Algorithm. The methods of metallographic image extraction are compared and the validity of the method is verified. And based on the American Society for Testing and Materials (ASTM) standards obtained grain size and other microstructure parameters.